https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/591261#M28919 I don't think there is a 'right approach'. I would describe the data including the reasons for missingness and then report both: the number of cases correctly identified by the test both including and excluding the missing cases. What is the right number to use will depend on the reasons for missingness and the intended uses of the summary. Tue, 24 Sep 2019 18:40:02 GMT Haris 2019-09-24T18:40:02Z https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/590748#M28914 <DIV class="js-vote-count grid--cell fc-black-500 fs-title grid fd-column ai-center">&nbsp;</DIV><DIV class="post-text"><P>I am using SAS to calculate sensitivity and specificity for a diagnostic test against the golden standard. Among 300 enrolled children 32 cases have the disease and 268 cases do not have the disease. The diagnostic test for which I want to calculate the specificity has 6 positives, 288 negatives and 6 missing values.</P><P>When I use</P><PRE><CODE>`` proc freq data=data; tables Test*Response; run; ``</CODE></PRE><P>I get different values for the specificity when I impute missing values with 999 (68.8%) and when I do not impute them (100%). What is the right approach? How missing values will influence on the specificity calculations ?</P><P>&nbsp;</P><P>Here is my data:</P><PRE><CODE>`` test response [1,] 0 0 [2,] 0 0 [3,] 1 1 [4,] 0 0 [5,] 0 0 [6,] 0 0 [7,] 1 1 [8,] 0 0 [9,] 0 0 [10,] 0 0 [11,] 0 0 [12,] 1 1 [13,] 0 0 [14,] 0 0 [15,] 0 0 [16,] 0 0 [17,] 0 0 [18,] 0 0 [19,] 0 0 [20,] 0 0 [21,] 0 0 [22,] 1 1 [23,] 0 0 [24,] 0 0 [25,] 0 0 [26,] 0 0 [27,] 0 0 [28,] 0 0 [29,] 0 0 [30,] 0 0 [31,] 0 1 [32,] 0 0 [33,] 0 0 [34,] NA 0 [35,] 0 0 [36,] 0 0 [37,] 0 0 [38,] 0 0 [39,] NA 1 [40,] 0 0 [41,] 1 1 [42,] 0 0 [43,] 0 0 [44,] 0 1 [45,] 0 0 [46,] 1 1 [47,] 0 0 [48,] 0 0 [49,] 0 0 [50,] 0 1 [51,] 0 0 [52,] 0 0 [53,] NA 0 [54,] 0 0 [55,] 0 0 [56,] 0 0 [57,] 0 0 [58,] 0 0 [59,] 1 1 [60,] 0 0 [61,] 1 1 [62,] 0 0 [63,] 0 0 [64,] 0 0 [65,] 0 0 [66,] 1 1 [67,] 0 0 [68,] 0 0 [69,] 0 0 [70,] 0 0 [71,] 0 0 [72,] 0 0 [73,] 0 0 [74,] 0 0 [75,] 0 0 [76,] 0 0 [77,] 0 0 [78,] 0 0 [79,] 0 0 [80,] 0 0 [81,] 0 0 [82,] 0 0 [83,] 1 1 [84,] 0 0 [85,] 0 0 [86,] 0 0 [87,] NA 1 [88,] 0 0 [89,] 0 0 [90,] 0 0 [91,] 0 0 [92,] 0 0 [93,] 0 0 [94,] 0 0 [95,] 0 0 [96,] 0 0 [97,] 0 0 [98,] 0 0 [99,] 0 0 [100,] 0 0 [101,] 0 0 [102,] 0 0 [103,] 0 0 [104,] 0 0 [105,] 0 0 [106,] 0 0 [107,] 0 0 [108,] 0 0 [109,] 0 0 [110,] 0 0 [111,] 0 0 [112,] 0 0 [113,] 0 0 [114,] 0 0 [115,] 0 0 [116,] 0 0 [117,] 0 0 [118,] 0 0 [119,] 0 0 [120,] 0 0 [121,] 0 0 [122,] 0 0 [123,] 0 0 [124,] 0 0 [125,] 1 1 [126,] 0 0 [127,] 0 0 [128,] 0 0 [129,] 0 0 [130,] 0 0 [131,] 0 0 [132,] 0 0 [133,] 0 0 [134,] 0 0 [135,] 0 0 [136,] 1 1 [137,] 0 0 [138,] 1 1 [139,] 0 0 [140,] 0 0 [141,] 0 0 [142,] 0 0 [143,] 0 0 [144,] 0 0 [145,] 0 0 [146,] 0 0 [147,] 0 0 [148,] 0 0 [149,] 0 0 [150,] 0 0 [151,] 1 1 [152,] 1 1 [153,] 0 0 [154,] 0 0 [155,] 0 0 [156,] 1 1 [157,] 0 0 [158,] 0 0 [159,] 0 0 [160,] 0 0 [161,] 0 0 [162,] 0 0 [163,] 0 0 [164,] 0 0 [165,] 0 0 [166,] 0 0 [167,] 0 0 [168,] 0 0 [169,] 0 0 [170,] 0 0 [171,] 1 1 [172,] 0 0 [173,] 0 0 [174,] 0 0 [175,] 0 0 [176,] 0 0 [177,] 0 0 [178,] 0 0 [179,] 0 0 [180,] 0 0 [181,] 0 0 [182,] 0 0 [183,] 0 0 [184,] 0 0 [185,] 0 0 [186,] 0 0 [187,] 0 0 [188,] 1 1 [189,] 0 0 [190,] 0 0 [191,] 0 0 [192,] 0 0 [193,] 0 1 [194,] 0 0 [195,] 0 0 [196,] 0 0 [197,] 0 1 [198,] NA 0 [199,] 1 1 [200,] 0 0 [201,] 0 0 [202,] 0 0 [203,] 0 0 [204,] 0 1 [205,] 0 0 [206,] 0 0 [207,] 0 0 [208,] 0 0 [209,] 0 0 [210,] 0 0 [211,] 0 0 [212,] 0 0 [213,] NA 0 [214,] 0 0 [215,] 0 0 [216,] 0 0 [217,] 0 0 [218,] 0 0 [219,] 0 0 [220,] 0 0 [221,] 0 0 [222,] 0 0 [223,] 0 0 [224,] 0 0 [225,] 0 0 [226,] 0 0 [227,] 0 0 [228,] 0 0 [229,] 0 0 [230,] 0 0 [231,] 0 0 [232,] 0 0 [233,] 0 0 [234,] 1 1 [235,] 1 1 [236,] NA 0 [237,] 0 0 [238,] 0 0 [239,] 0 0 [240,] 0 0 [241,] 0 0 [242,] 0 0 [243,] 0 0 [244,] 0 0 [245,] 0 0 [246,] 0 0 [247,] 0 0 [248,] 0 0 [249,] 0 0 [250,] 0 0 [251,] 0 0 [252,] 0 0 [253,] 0 0 [254,] 0 0 [255,] 0 0 [256,] 0 0 [257,] 0 0 [258,] 0 0 [259,] 0 0 [260,] 1 1 [261,] 0 0 [262,] 0 0 [263,] 0 0 [264,] 0 0 [265,] 0 0 [266,] 0 0 [267,] 0 0 [268,] 0 0 [269,] 0 0 [270,] 0 0 [271,] 0 0 [272,] NA 1 [273,] 0 0 [274,] 0 0 [275,] 0 0 [276,] 0 0 [277,] 0 0 [278,] 0 0 [279,] 0 0 [280,] 0 0 [281,] 0 0 [282,] 0 0 [283,] 0 0 [284,] 0 1 [285,] 0 0 [286,] 0 0 [287,] 0 0 [288,] 0 0 [289,] 0 0 [290,] 0 0 [291,] 0 0 [292,] 0 0 [293,] 0 0 [294,] 0 0 [295,] 0 0 [296,] 0 0 [297,] NA 0 [298,] 0 0 [299,] 0 0 [300,] 0 0</CODE></PRE></DIV> Sun, 22 Sep 2019 16:55:44 GMT https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/590748#M28914 ph6 2019-09-22T16:55:44Z https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/591261#M28919 I don't think there is a 'right approach'. I would describe the data including the reasons for missingness and then report both: the number of cases correctly identified by the test both including and excluding the missing cases. What is the right number to use will depend on the reasons for missingness and the intended uses of the summary. Tue, 24 Sep 2019 18:40:02 GMT https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/591261#M28919 Haris 2019-09-24T18:40:02Z https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/591738#M28937 Thanks for your reply, the reason for the missingness is that the test hasn't been achieved from those samples. Thu, 26 Sep 2019 00:15:59 GMT https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/591738#M28937 ph6 2019-09-26T00:15:59Z https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/592243#M28944 <P>What do you mean by "w<SPAN>hen I impute missing values with 999 (68.8%)."&nbsp; Can you show the code you are using?</SPAN></P> <P>&nbsp;</P> Fri, 27 Sep 2019 17:04:37 GMT https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/592243#M28944 Rick_SAS 2019-09-27T17:04:37Z https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/593456#M28987 <P>I am using the following code to impute the missing values with 999.</P><P>&nbsp;</P><P>data lab_results1;<BR />set lab_results;<BR />array Nums[*] _numeric_;<BR />do i = 1 to dim(Nums);<BR />if Nums[i] = . then Nums[i] = 999;<BR />end;<BR />run;</P> Wed, 02 Oct 2019 16:24:32 GMT https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/593456#M28987 ph6 2019-10-02T16:24:32Z https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/593472#M28988 <P>So you replaced the missing values with the value 999? Why?</P> <P>&nbsp;</P> <P>Note that if you are using PROC FREQ you can just use the / MISSING option on the TABLES statement to have it include the missing values when generating the cross-tab.</P> <P>&nbsp;</P> <PRE><CODE class=" language-sas">tables Test*Response / missing;</CODE></PRE> <P>&nbsp;</P> <P>If you have the 999 values instead of missing value and you want to exclude them then add a WHERE clause to your PROC FREQ step.</P> <PRE><CODE class=" language-sas">where test ne 999 and response ne 999; tables Test*Response ;</CODE></PRE> <P>&nbsp;</P> Wed, 02 Oct 2019 17:01:50 GMT https://communities.sas.com/t5/Statistical-Procedures/How-to-handle-missing-values-when-calculating-specificity-for-a/m-p/593472#M28988 Tom 2019-10-02T17:01:50Z